Runner: <LogsViewRunner nb_logs=62 exit_code=1>

[tiandaoyuxi]

[2024-11-01 09:14:31] [INFO] Traceback (most recent call last): [2024-11-01 09:14:31] [INFO] File "", line 198, in _run_module_as_main [2024-11-01 09:14:31] [INFO] File "", line 88, in _run_code [2024-11-01 09:14:31] [INFO] File "C:\Users\win11.conda\envs\fluxgym\Scripts\accelerate.exe__main__.py", line 7, in [2024-11-01 09:14:31] [INFO] File "C:\Users\win11.conda\envs\fluxgym\Lib\site-packages\accelerate\commands\accelerate_cli.py", line 48, in main [2024-11-01 09:14:31] [INFO] args.func(args) [2024-11-01 09:14:31] [INFO] File "C:\Users\win11.conda\envs\fluxgym\Lib\site-packages\accelerate\commands\launch.py", line 1106, in launch_command [2024-11-01 09:14:31] [INFO] simple_launcher(args) [2024-11-01 09:14:31] [INFO] File "C:\Users\win11.conda\envs\fluxgym\Lib\site-packages\accelerate\commands\launch.py", line 704, in simple_launcher [2024-11-01 09:14:31] [INFO] raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd) [2024-11-01 09:14:31] [INFO] subprocess.CalledProcessError: Command '['C:\Users\win11\.conda\envs\fluxgym\python.exe', 'sd-scripts/flux_train_network.py', '--pretrained_model_name_or_path', 'D:\fluxgym\models\unet\flux1-dev.sft', '--clip_l', 'D:\fluxgym\models\clip\clip_l.safetensors', '--t5xxl', 'D:\fluxgym\models\clip\t5xxl_fp16.safetensors', '--ae', 'D:\fluxgym\models\vae\ae.sft', '--cache_latents_to_disk', '--save_model_as', 'safetensors', '--sdpa', '--persistent_data_loader_workers', '--max_data_loader_n_workers', '2', '--seed', '42', '--gradient_checkpointing', '--mixed_precision', 'bf16', '--save_precision', 'bf16', '--network_module', 'networks.lora_flux', '--network_dim', '4', '--optimizer_type', 'adamw8bit', '--sample_prompts=D:\fluxgym\outputs\lbttest\sample_prompts.txt', '--sample_every_n_steps=2', '--learning_rate', '8e-4', '--cache_text_encoder_outputs', '--cache_text_encoder_outputs_to_disk', '--fp8_base', '--highvram', '--max_train_epochs', '16', '--save_every_n_epochs', '4', '--dataset_config', 'D:\fluxgym\outputs\lbttest\dataset.toml', '--output_dir', 'D:\fluxgym\outputs\lbttest', '--output_name', 'lbttest', '--timestep_sampling', 'shift', '--discrete_flow_shift', '3.1582', '--model_prediction_type', 'raw', '--guidance_scale', '1', '--loss_type', 'l2']' returned non-zero exit status 1. [2024-11-01 09:14:31] [ERROR] Command exited with code 1 [2024-11-01 09:14:31] [INFO] Runner:

[Djanghost]

Same here, can't use fluxgym anymore

[AkiraToya]

So, is this unsolvable? I also got this error. I previously think my system can't handle it ( but no cuda oom etc ), just like above. Then I find one that can be used on google colab, also the same. Got this error.